 Main Predicate and Their Arguments as Explanation Signals For Intent ClassificationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 |
 Interpreting Sentiment Composition with Latent Semantic TreeAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 MDACE: MIMIC Documents Annotated with Code EvidenceAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Quantifying Context Mixing in TransformersConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 |
 Going Beyond XAI: A Systematic Survey for Explanation-Guided LearningACM Computing Surveys (ACM CSUR), 2022 |
 StyLEx: Explaining Style Using Human Lexical AnnotationsConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
 VisFIS: Visual Feature Importance Supervision with
Right-for-the-Right-Reason ObjectivesNeural Information Processing Systems (NeurIPS), 2022 |
 Interpreting Language Models with Contrastive ExplanationsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Kayo Yin Graham Neubig |
 Explainable Deep Learning in Healthcare: A Methodological Survey from an
Attribution ViewWIREs Mechanisms of Disease (WIREs Mech Dis), 2021 |
 The Out-of-Distribution Problem in Explainability and Search Methods for
Feature Importance ExplanationsNeural Information Processing Systems (NeurIPS), 2021 |
 Do Context-Aware Translation Models Pay the Right Attention?Annual Meeting of the Association for Computational Linguistics (ACL), 2021 |
 Explain and Predict, and then Predict AgainWeb Search and Data Mining (WSDM), 2021 |
 FastIF: Scalable Influence Functions for Efficient Model Interpretation
and DebuggingConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 Evaluating Explanations: How much do explanations from the teacher aid
students?Transactions of the Association for Computational Linguistics (TACL), 2020 Danish Pruthi Rachit Bansal Bhuwan Dhingra Livio Baldini Soares Michael Collins Zachary Chase Lipton Graham Neubig William W. Cohen |
 Weakly Supervised Medication Regimen Extraction from Medical
ConversationsClinical Natural Language Processing Workshop (ClinicalNLP), 2020 |
 Learning to Faithfully Rationalize by ConstructionAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 ERASER: A Benchmark to Evaluate Rationalized NLP ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Detecting and Reducing Bias in a High Stakes DomainConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
